From b7df8f90a7d749ce609e7ff344464db73329117a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 12 May 2019 10:23:36 +0100 Subject: [PATCH 1/4] [yahoo:gyao] add X-User-Agent header to dam proxy requests(closes #21071) --- youtube_dl/extractor/yahoo.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 6576c1d69..a3b5f00c8 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -511,6 +511,8 @@ class YahooGyaOPlayerIE(InfoExtractor): 'https://gyao.yahoo.co.jp/dam/v1/videos/' + video_id, video_id, query={ 'fields': 'longDescription,title,videoId', + }, headers={ + 'X-User-Agent': 'Unknown Pc GYAO!/2.0.0 Web', }) return { '_type': 'url_transparent', From e6a25fea23c4ee1db2461e77b457d01dc922a0a6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 12 May 2019 23:23:29 +0700 Subject: [PATCH 2/4] [svtplay] Update API URL (closes #21075) --- youtube_dl/extractor/svt.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/svt.py b/youtube_dl/extractor/svt.py index 7aa1b5919..0901c3163 100644 --- a/youtube_dl/extractor/svt.py +++ b/youtube_dl/extractor/svt.py @@ -185,7 +185,7 @@ class SVTPlayIE(SVTPlayBaseIE): def _extract_by_video_id(self, video_id, webpage=None): data = self._download_json( - 'https://api.svt.se/video/%s' % video_id, + 'https://api.svt.se/videoplayer-api/video/%s' % video_id, video_id, headers=self.geo_verification_headers()) info_dict = self._extract_video(data, video_id) if not info_dict.get('title'): From 0e0bfd334c59bd9a0bf4e24e88237041b7ff411d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 13 May 2019 00:11:48 +0700 Subject: [PATCH 3/4] [tele5] Relax _VALID_URL (closes #21020, closes #21063) --- youtube_dl/extractor/tele5.py | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py index 25573e49f..0b346d7be 100644 --- a/youtube_dl/extractor/tele5.py +++ b/youtube_dl/extractor/tele5.py @@ -7,7 +7,7 @@ from ..compat import compat_urlparse class Tele5IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P[^?#&]+)' + _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416', 'info_dict': { @@ -21,10 +21,22 @@ class Tele5IE(InfoExtractor): 'skip_download': True, }, }, { - 'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191', + 'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191', 'only_matching': True, }, { - 'url': 'https://www.tele5.de/tv/dark-matter/videos', + 'url': 'https://www.tele5.de/video-clip/?ve_id=1609440', + 'only_matching': True, + }, { + 'url': 'https://www.tele5.de/filme/schlefaz-dragon-crusaders/', + 'only_matching': True, + }, { + 'url': 'https://www.tele5.de/filme/making-of/avengers-endgame/', + 'only_matching': True, + }, { + 'url': 'https://www.tele5.de/star-trek/raumschiff-voyager/ganze-folge/das-vinculum/', + 'only_matching': True, + }, { + 'url': 'https://www.tele5.de/anders-ist-sevda/', 'only_matching': True, }] From a277dd33ebc7b3a3d4a7cf603ccdbe2d9ec5d73b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 13 May 2019 00:13:00 +0700 Subject: [PATCH 4/4] [tele5] Improve video id extraction --- youtube_dl/extractor/tele5.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py index 0b346d7be..33a72083b 100644 --- a/youtube_dl/extractor/tele5.py +++ b/youtube_dl/extractor/tele5.py @@ -48,8 +48,9 @@ class Tele5IE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_id = self._html_search_regex( - r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)', - webpage, 'video id') + (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)', + r'\s+id\s*=\s*["\']player_(\d{6,})', + r'\bdata-id\s*=\s*["\'](\d{6,})'), webpage, 'video id') return self.url_result( 'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,